Calibration drift in regression and machine learning models for acute kidney injury.

Journal: Journal of the American Medical Informatics Association : JAMIA

Published Date: Nov 1, 2017

Abstract

OBJECTIVE: Predictive analytics create opportunities to incorporate personalized risk estimates into clinical decision support. Models must be well calibrated to support decision-making, yet calibration deteriorates over time. This study explored the influence of modeling methods on performance drift and connected observed drift with data shifts in the patient population.

Authors

Sharon E Davis

Vanderbilt University School of Medicine, Nashville, TN.
Thomas A Lasko

Vanderbilt University School of Medicine, Nashville, TN.
Guanhua Chen

Vanderbilt University School of Medicine, Nashville, TN.
Edward D Siew

Department of Nephrology, Nephrology Vanderbilt O'Brien Center for Kidney Disease, Nashville, TN, United States.
Michael E Matheny

Vanderbilt University School of Medicine, Nashville, TN.

Keywords

Acute Kidney Injury Aged Bayes Theorem Clinical Decision-Making Decision Support Techniques Female Hospitals, Veterans Humans Logistic Models Machine Learning Male Middle Aged United States

External Resources

View on PubMed Access via DOI PubMed (28379439)

Calibration drift in regression and machine learning models for acute kidney injury.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals